JP2013086226A - Communication robot - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a communication robot which allows a user to more easily to talk with the robot and to have friendly feeling therefor when speaking to the robot.SOLUTION: The communication robot includes voice detection means detecting spoken words uttered by the user and reaction expressing means expressing prescribed responsive reactions. The communication robot is made to react with spoken words of the user and to express responsive reactions of a plurality of the predetermined patterns. At this time, the robot carries out at least one of the determination of whether the spoken words are normal expressions, whether the spoken words are agreement request expressions, and whether the spoken words are assertive expressions, and the robot is made to express different responsive reactions based on determination results.

Description

  The present invention relates to a communication robot that generates a body motion from detected voice.

  Development of communication robots (hereinafter also simply referred to as “robots”) for the purpose of communicating with human beings is underway. This type of robot includes not only verbal communication by words but also non-verbal communication by body movement (hereinafter referred to as “listener movement”) such as changing facial expressions and performing gestures.

  According to the robot that performs such a listener operation, when a human talks to the robot, a posture to listen to the robot is formed. As a result, a person who is a speaker can feel natural communication as if he / she is talking to a person, and does not feel uncomfortable that he / she is talking to an object. Therefore, when talking to the robot, a so-called pull-in effect that makes it easier for humans to speak can be achieved. Such a robot is disclosed in Non-Patent Document 1, for example.

Tomio Watanabe, “With the development of physical communication system E-COSMIC where physical communication is drawn and physicality”, “Baby Science 2002. Vol. Publication

  In recent years, research related to the coexistence of humans and robots has attracted attention. In other words, people's knowledge acquisition in various living environments such as hospitals and other public facilities, restaurants and other commercial facilities, schools and other educational facilities, game centers and other recreational facilities, and care centers and other nursing homes Robots that help or work with people are widely developed.

  The present inventors considered the development of a robot that supports the emotional aspect of human social life as a robot that coexists with such a person. Specifically, we considered that the stress of human beings due to social life can be eliminated by robot movement.

  As a result of the inventors investigating the means for relieving stress, it has been found that listening to bitches is effective in relieving stress. However, when a person complains about a robot, if the robot performs a conventional listener operation, the person cannot sufficiently relieve stress.

The following reasons can be considered for this. In general, when complaining, a speaker can easily complain by showing the attitude that the listener listens to the other person's remarks. Also, if the listener strongly agrees with the listener, the wad will disappear and the feeling will improve. In other words, when listening to bitches, the listener is required to have a stronger empathy for the speaker than when conducting a normal conversation.
However, in the listener operation performed by the conventional robot, the user who is a speaker cannot fully feel that he / she is sympathetic with the utterance content.

  Therefore, an object of the present invention is to provide a communication robot that allows a user to speak more easily and feel more familiar when the user speaks toward the robot.

  One aspect of the present invention for solving the above-described problems is that a voice detection unit that detects spoken words emitted by a user and a reaction table that expresses a predetermined response response that the user can visually and / or auditorily know. A communication robot that responds to a user's spoken word and the response expression means expresses a plurality of patterns of response responses determined in advance, the content of the spoken word detected by the voice detection means Voice determination means for determining, wherein the voice determination means determines whether or not the spoken word is a normal expression, determines whether or not the spoken word is a consent request expression, and whether or not the spoken word is an assertive expression It is a communication robot capable of determining at least one of determination of whether or not, and displaying different response responses based on the determination result of the sound determination means

In one aspect of the present invention, a voice determination unit that determines the content of a spoken word is provided, and the content of the spoken word of a user who is a speaker can be determined. Then, it is possible to express an appropriate response response according to the content of the determined spoken language. For example, depending on the content of the user's conversation, operations such as hitting, agreeing, and strongly agreeing can be switched. As a result, the response of the robot is close to that of a human (animal), and natural communication is established with the user. This has the effect of making it easier to talk when the user talks to the robot.
Furthermore, by displaying an appropriate response response according to the content of the user's story, the user can feel that the other party (robot) is strongly sympathizing with his / her opinion. . Specifically, when the user is speaking, if the user performs a predetermined operation such as putting a match at an appropriate timing, the user feels that the other party (robot) is listening to his / her speech. When the predetermined operation is an operation indicating approval or consent, for example, shaking the head vertically, the user feels as if the talking partner (robot) has agreed to the content of the talk. And the user feels that the other party (robot) is strongly sympathetic to his / her opinion because the other party (robot) listens and agrees eagerly. From this, there is an effect that the user feels more familiar with the talking partner (robot).
Here, the robot includes a tangible object (device, hardware, doll) that operates according to a program.

  The second aspect of the present invention includes voice detection means for detecting a spoken language spoken by the user, and reaction expression means for expressing a predetermined response response that the user can visually and / or audibly know. And a voice determination means for determining the content of the spoken language detected by the voice detection means, wherein the response expression means responds to the user's spoken language and the response expression means expresses a plurality of predetermined response responses. The speech determination means includes the content of the spoken word based on at least one of the sound at the end of the spoken word or the sound near the word ending, the length of the spoken word, or the strength of the voice. The communication robot is characterized in that different response responses are expressed based on the determination result of the voice determination means.

In the second aspect of the present invention, there is a voice determination means for determining the content of the spoken word, and information such as the sound at the end of the spoken word, the sound near the word ending, the length of the spoken word, the voice strength, etc. Therefore, the content of spoken language can be determined. Then, it is possible to express an appropriate response response according to the content of the determined spoken language. That is, similarly to the above-described aspect, by changing the response response according to the content of the story, the response of the robot becomes close to the response of a human, and natural communication with the user is established. This has the effect of making it easier to talk when the user talks to the robot.
In addition, by expressing an appropriate response response according to the content of the user's story, as with the above-described mode, the user is told that the other party (robot) is strongly sympathetic to his / her opinion. Can be felt, and the user can feel familiar.

  According to a third aspect of the present invention, in the communication robot according to the aspect described above, the voice determination means determines the content of the spoken word based on the final particle of the spoken word uttered by the user.

In the third aspect of the present invention, the content of the spoken word is determined based on the final particle of the spoken word emitted by the user. As a result, it is possible to carry out the determination with an algorithm that is relatively easy to implement as compared with the case where the content of spoken words is determined from the entire sentence or phrase. Moreover, since the content of the spoken word is not determined from the whole sentence or phrase, it is possible to obtain a determination result quickly at the time of execution.
The term final particle as used herein includes an interposition particle, and more specifically includes a general part of speech that adds meaning to the end of a sentence or phrase. Furthermore, in a foreign language such as English or German, a part added to the end of a sentence or phrase, such as a part at the end of an additional question sentence, is added.

  According to a fourth aspect of the present invention, in the communication robot according to the aspect described above, the response reaction is a different response reaction by changing the number of executions of a specific operation. Based on this, the number of times of performing the specific operation varies.

  In the fourth aspect of the present invention, different response responses are obtained by changing the number of executions of a specific operation. That is, by repeating the same operation, the meaning indicated by the operation is strengthened. For example, it can be shown that the latter agrees more strongly in the case where the robot performs the operation of whispering once and the case where the robot performs the operation of whispering multiple times. Therefore, depending on the difference in the number of times of the same operation, two types of responses can be performed: a response expressing that the user agrees and a response expressing that the user strongly agrees. In this way, by changing the number of executions of a specific operation, if the response response is different, the response response to the user's spoken language becomes closer to a human response.

According to a fifth aspect of the present invention, in the communication robot according to the aspect described above, the voice determination means includes one or more selected from the following words (1) to (4) whose endings of the spoken language the user utters: If it is a word, it is determined that it is a consent request expression.
(1) "Ne"
(2) "U"
(3) "O"
(4) "ka"

In the fifth aspect of the present invention, the consent request expression is determined when the ending of the spoken language given by the user is one or more words selected from the words (1) to (4).
If the user speaks in Japanese and the ending of the spoken word is one or more words selected from the words (1) to (4) above, request consent from the user The possibility is high enough. Therefore, in such a case, it is possible to improve the accuracy of the determination operation for determining the content of the spoken word by determining that the content of the spoken word is the consent request expression.

According to a sixth aspect of the present invention, in the communication robot according to the aspect described above, the voice determination unit is configured such that the ending of a spoken word uttered by the user is selected from the following words (5) and (6): If it is a word, it is determined to be an assertive expression.
(5) "Da"
(6) "Ya"

In the sixth aspect of the present invention, when the ending of a spoken word uttered by the user is one or two words selected from the above words (5) and (6), it is determined as an asserted expression.
If the user speaks in Japanese and the ending of the spoken word is one or two words selected from the words (5) and (6) above, there is a possibility that the content spoken by the user has been determined Is high enough. Therefore, in such a case, it is possible to improve the accuracy of the determination operation for determining the content of the spoken word by determining that the content of the spoken word is the asserted expression.

  According to a seventh aspect of the present invention, in the communication robot according to the aspect described above, the communication robot has a shape imitating a person or an animal.

In the seventh aspect of the present invention, the shape of the robot is generally simplified and omitted by exaggerating and emphasizing humans and animals, or their characteristics, which are generally familiar to people and easy to talk to. As a result, when the user talks to the robot, the user's uncomfortable feeling that he / she is talking to the object can be more reliably eliminated, and the user can speak more easily.
Here, “human or animal” includes non-existing characters such as movies, novels, comics, etc., and anthropomorphic symmetric objects.

According to an eighth aspect of the present invention, in the communication robot according to the aspect described above, the response reaction is a composite of one or more operations selected from the following operations (1) to (3). To do.
(1) whisper (2) cry (3) move one of the four legs

  In the eighth aspect of the present invention, since the robot expresses a response response as if a human or animal performs, when the user talks to the robot, the robot seems to talk to the human or animal. Can give an impression. For this reason, the user does not feel uncomfortable that he / she is talking to an object, and the user can speak more easily.

According to a ninth aspect of the present invention, in the communication robot according to the aspect described above, the voice determination means includes one or two or more selected from the following words (1) to (4) whose endings of the spoken language the user utters: It is determined that it is a consent request expression, and when the ending of the spoken word that the user utters is one or two words selected from the following words (5) and (6), When the spoken language that the user utters is not the consent request expression and the assertion expression, it is determined as a normal expression, and the response response is a different response response by changing the number of times the crawl operation is performed. In this case, the number of snooping operations to be performed when it is determined as the consent request expression is larger than the number of snooping operations to be performed when it is determined as the normal expression, and is performed when it is determined as the assertion expression. Moving The number is characterized by more than the number of operations nods to be carried out when it is determined that the consent request representation.
(1) "Ne"
(2) "U"
(3) "O"
(4) "ka"
(5) "Da"
(6) "Ya"

  In the ninth aspect of the present invention, the determination operation for determining the content of the spoken word can be performed with high accuracy, and a response response like a human is expressed based on the determined content of the spoken word. More specifically, depending on the content of the spoken language, it may be asked a few times so as to strike a conflict, or it may be asked many times so as to show a strong agreement. As a result, the response of the robot becomes closer to that of a human, and natural communication with the user is established. This has the effect of making it easier to talk when the user talks to the robot. Furthermore, by displaying a response response that matches the content of the spoken language, as described above, the user can feel that the other party (robot) is strongly sympathizing with their opinions. . From this, there is an effect that the user feels more familiar with the talking partner (robot).

In the present invention, since the response of the robot is close to that of a human (animal), more natural communication can be established with the user. Therefore, when the user talks to the robot, there is an effect that it becomes easy to speak.
Further, according to the present invention, when the user speaks to the robot, the robot expresses an appropriate response response according to the content of the story. This can give the user the impression that the other party (robot) is strongly sympathetic to his / her opinion. This has the effect of making the user feel familiar with the robot.

1 is a perspective view showing a robot according to a first embodiment of the present invention. It is a block diagram which shows the electric constitution of the robot of FIG. It is a flowchart which shows the operation | movement procedure of the communication operation | movement of the robot of FIG. It is a perspective view which shows the robot which concerns on embodiment different from the robot of FIG. It is a perspective view which shows the robot which concerns on embodiment different from the robot of FIG.

  Hereinafter, although each embodiment of the present invention is described, the present invention is not limited to these examples.

  The robot 1 (communication robot) of the first embodiment of the present invention acquires spoken words as utterance information when the user speaks. Then, based on the acquired utterance information and the action program stored in the memory, a prescribed communication operation is performed.

  Hereinafter, such a robot will be described in detail.

  As shown in FIG. 1, the robot 1 has a shape imitating a person, and includes a body 2, a head 3, a hand 4, and a foot 5 attached to the body 2.

  The head 3 (reaction display means) is attached to the body 2 via a mechanical structure formed by a motor, a cam mechanism, a crank mechanism, etc. (not shown). Therefore, the head 3 can perform an operation (response reaction) for rotating and tilting the posture with respect to the body 2. In other words, the head 3 is attached in a state where it can be moved and shaken.

  Further, the hand portion 4 and the foot portion 5 are also attached to the body 2 via the mechanical structure portion, and the tip of the hand portion 4 and the tip of the foot portion 5 can swing with respect to the body 2. That is, the hand part 4 and the foot part 5 are attached in a state in which operations such as shaking hands and raising a leg are possible.

Next, the electrical configuration of the robot 1 will be described with reference to FIG.
The robot 1 includes a CPU 15, a memory 16, and a microphone 17 (voice detection means), which are connected via a bus. Further, the CPU 15 is connected to the dialogue content DB 18 and the dialogue action DB 19 via a bus.

  The CPU 15 is a well-known CPU and is also referred to as a microprocessor, and can process information by reading and executing a program on a storage device.

  The memory 16 is a storage device including what is called an auxiliary storage device or secondary storage device such as a flash memory or HDD in addition to a ROM such as an EPROM or an EEPROM, a RAM such as a DRAM or an SDRAM, and a combination of these. Configured. The memory 16 stores various programs and data mainly including a voice analysis unit 22 and a dialogue action execution unit 23 for controlling the operation of the robot 1. The memory 16 may be constituted by an external storage device such as a hard disk, a floppy disk (registered trademark), an MO, a CD, a DVD, a BD, a magnetic tape, and the like and a reading device thereof.

  The voice analysis unit 22 has a function of specifying the content (expression type) of speech information based on a signal representing speech information transmitted from the microphone 17 and information stored in a dialogue content DB 18 described later.

  The dialogue action execution unit 23 is a function for causing the robot 1 to execute a specific operation based on the content (expression type) of the utterance information identified by the voice analysis unit 22 and information stored in the dialogue content DB 18 described later. Have

  The microphone 17 is a well-known microphone and can collect external sound and convert it into an electrical signal.

  The dialogue content DB 18 stores a word that can be the end of a conversation and an expression type in association with each other. In the present embodiment, a group of words including six words “ne”, “u”, “o”, “ka”, “da”, “ya”, and a word (phrase) having these as the last word , A group of expressions including “consent request expression” and “conclusive expression” are stored in association with each other. More specifically, at least four words “ne”, “u”, “o”, “ka”, and a word having these as the last word are associated with “consent request expression”. Two words “da” and “ya”, and a word having these words as the last word and a “definite expression” are stored in association with each other.

  The dialogue action DB 19 stores the type of expression and the operation of the robot 1 in association with each other. In this embodiment, the robot 1 includes a group of expression types including “conclusive expression”, “consent request expression”, “normal expression”, and “roaming three times”, “twisting twice”, and “single once”. A group of actions is stored in association with each other. More specifically, at least the operations of “declaration expression” and “3 times of singing”, “consent request expression” and “twice of two times”, “normal expression” and “single of once” are associated. Is remembered.

When the user speaks, the robot 1 of the present invention performs a communication operation according to the utterance content. This communication operation makes the response of the robot 1 close to a human response, and natural communication is established between the user and the robot 1.
A communication operation which is a characteristic operation of the present invention will be described in detail below with reference to FIG.

When the user speaks to the robot 1, the robot 1 acquires voice as speech information by the microphone 17 (step 1). And if CPU15 confirms that the signal showing speech information was emitted from the microphone 17, the speech analysis part 22 will perform the analysis of speech information (step 2). That is, the utterance information is divided into sentences as necessary, and the ending sound or the sound near the ending is specified from the extracted contents of one sentence. Then, the sound of the specified ending or near the ending is compared with the information stored in the dialogue content DB 18.
In addition, when the speech information is divided for each sentence, it is based on information such as the time when the voice between the sentences was not emitted, the strength of the sound in the utterance information (inflection), the time since the voice was emitted, etc. Identify the sentence.

  At this time, when the sound at the end of the utterance information or the sound near the end of the utterance is a word associated with the “definite expression” (Yes in step 3), the CPU 15 determines the correspondence by the interactive action execution unit 23. The operation is performed (step 4). That is, the action that the robot 1 should perform on the utterance expression based on the analysis result of the utterance information by the voice analysis unit 22 in which the content of the utterance information is “conclusive expression” and the information stored in the dialogue action DB 19. And the robot 1 is caused to execute the specified action. More specifically, the phrase that constitutes the sentence specified from the utterance information, or the sentence that is located at the end of the sentence, or the sound, and the word that can be the ending of the conversation stored in the dialogue action DB 19 And compare. In the present embodiment, when it is specified that the content of the utterance information is “conclusive expression”, the robot 1 performs the “three times” operation.

  On the other hand, when the sound at the end of the utterance information or the sound near the end of the utterance information is not a word associated with the “conclusive expression” (No in step 3), but is a word associated with the “consent request expression” ( When the answer is Yes in Step 5), the CPU 15 performs the consent handling operation by the dialogue action executing unit 23 (Step 6). That is, in the same manner as described above, the action to be performed by the robot 1 on the utterance expression is specified from the analysis result of the utterance information by the voice analysis unit 22 and the information stored in the dialogue action DB 19, and the specified action is specified. Is executed by the robot 1. In the present embodiment, when it is specified that the content of the utterance information is “consent request expression”, the robot 1 performs a “twisting twice” operation.

  Furthermore, when the sound at the end of the utterance information or the sound near the end of the utterance information is not a word associated with the “definite expression”, but is not a word associated with the “consent request expression” (in steps 3 and 5). When both are No), the CPU 15 performs the normal response operation by the dialogue action execution unit 23 (step 7). That is, as a result of the analysis of the utterance information by the voice analysis unit 22, if the utterance information content is determined to be a normal one that does not need to execute a specific operation, the utterance information content is “normal expression”. Is identified. And the action which the robot 1 should perform with respect to the utterance expression is specified from the type of the specified expression and the information stored in the dialogue action DB 19, and the robot 1 is caused to execute the specified action. That is, the robot 1 is caused to execute an action for a normal utterance. In this embodiment, when it is specified that the content of the utterance information is “normal expression”, the robot 1 performs the “single once” operation.

  Thus, while the user is speaking, the robot 1 performs the operations from Step 1 to Step 7 described above.

  When the robot 1 executes such a communication operation, natural communication is established between the user and the robot 1. That is, the user can see the discomfort of talking to the machine, and can visually recognize the attitude that the partner (robot 1) is listening to his / her speech. For this reason, the user feels as if the robot 1 is sympathetic with the content of his / her utterance, and is in the same state as when he / she asks the person to listen to the bitches. As a result, an effect that the stress of the user can be eliminated can be achieved.

  This is the end of the description of the communication operation.

  The association (table configuration) between the dialogue content DB 18 and the dialogue action DB 19 in the above embodiment is merely an example, and the association (table configuration) of information stored in the database is a configuration that can realize the technical idea of the present invention. Anything can be used.

  Therefore, the number of databases is not limited to two. There may be one or a plurality of three or more. That is, information necessary for realizing the technical idea of the present invention, such as the word constituting the tail part of the speech information, the type of expression, and the behavior of the robot, may be stored in association with each other.

  In the above-described embodiment, the sound at the end of the word or the sound near the end of the word and the expression type are stored in association with each other. However, the present invention is not limited to this. For example, the length of speech information, the strength of voice, and / or the final particle may be stored in association with the type of expression. That is, it suffices if the type of expression of the speech information can be specified from the signal representing the speech information and the stored information.

  In the above-described embodiment, the data is constructed assuming that the user speaks to the robot 1 using a Japanese standard language, but the present invention is not limited to this. For example, the sound at the end of the word associated with the type of expression or the sound near the end of the word may be assumed to be a foreign language, or may be assumed to be a dialect. That is, the robot 1 of the present invention may correspond to any or all of Japanese, foreign languages, or dialects thereof.

In the above-described embodiment, in order for the user himself / herself to feel that the robot 1 is sympathetic with the content of the user's utterance, the robot 1 is in the “definite expression”, “consent request expression”, and “normal expression”. We performed actions that strongly agreed in order. In other words, the strength of consent was made different by increasing the number of responses (response reactions) in the order of “conclusive expression”, “consent request expression”, and “normal expression”. However, the communication operation performed by the robot of the present invention is not limited to this. For example, different responses may be executed by executing different operations for each of “conclusive expression”, “consent request expression”, and “normal expression”. That is, it is only necessary to determine the strength of the necessary consent based on the acquired utterance information and reference information stored in advance, and to display a response response according to the determined result.
Therefore, the operation to be executed as a response reaction is not limited to the operation of moving the head 3 such as scooping, but may be the operation of moving the hand 4 or the foot 5. However, it is more natural for the communication between the user and the robot to cause the robot 1 to execute an action such as whispering to an utterance, that is, an action that can be actually taken when a person listens to another person's story. ,desirable.

  In the above-described embodiment, the robot 1 imitates a person, but the present invention is not limited to this. For example, as shown in FIG. 4, a robot 50 having a more inorganic shape may be used. That is, the shape of the head is not limited to a rounded shape, but may be a square. Further, the shape of the tip of the hand portion may be a substantially C-shape. Moreover, the robot 51 imitating animals, such as a dog, as shown in FIG. 5 may be used. In this case, the response operation may be an operation such as ringing, barking, moving the extremity, moving the tail, moving the ear, and the like. More specifically, it may be an anthropomorphic person who does not exist, such as a movie, a novel, or a creation such as a comic, or a symmetric object. However, a shape imitating a person is desirable because it is predicted that the effect of allowing the user to talk without a sense of incongruity will be higher.

1,50,51 Robot (communication robot)
3 head (reaction expression means)
17 Microphone (voice detection means)
22 Voice analysis unit (voice judgment means)

Claims (9)

It has voice detection means for detecting spoken language spoken by the user, and reaction expression means for expressing a predetermined response response that the user can know visually and / or auditorily, and reacts to the user's spoken language. The communication robot is a communication robot that displays a plurality of patterns of response responses.
Having a voice determination means for determining the content of the spoken word detected by the voice detection means;
The voice determination means is at least one of determination of whether or not the spoken word is a normal expression, determination of whether or not the spoken word is an agreement request expression, and determination of whether or not the spoken word is an asserted expression Judgment is possible,
A communication robot characterized in that different response responses are expressed based on the determination result of the voice determination means. It has voice detection means for detecting spoken language spoken by the user, and reaction expression means for expressing a predetermined response response that the user can know visually and / or auditorily, and reacts to the user's spoken language. The communication robot is a communication robot that displays a plurality of patterns of response responses.
Having a voice determination means for determining the content of the spoken word detected by the voice detection means;
The voice determination means determines what the content of the spoken word is based on at least one of the information of the sound at the end of the spoken word or the sound near the word ending, the length of the spoken word, or the strength of the voice. Judgment,
A communication robot characterized in that different response responses are expressed based on the determination result of the voice determination means.   The communication robot according to claim 1, wherein the voice determination unit determines the content of the spoken word based on a final particle of the spoken word uttered by the user.   The response response is a different response response by changing the number of executions of the specific operation, and the number of times of executing the specific operation changes based on the determination result of the voice determination means. The communication robot according to any one of claims 1 to 3. The voice determination means determines that the utterance of the spoken word uttered by the user is an agreement request expression when it is one or more words selected from the following words (1) to (4): The communication robot according to any one of claims 1 to 4.
(1) "Ne"
(2) "U"
(3) "O"
(4) "ka" The voice determination means determines that the spoken word uttered by the user is an affirmative expression when the ending of the spoken word is one or two words selected from the following words (5) and (6): Item 6. The communication robot according to any one of Items 1 to 5.
(5) "Da"
(6) "Ya"   The communication robot according to claim 1, wherein the communication robot has a shape imitating a person or an animal. The communication robot according to claim 7, wherein the response reaction is a combination of one or two or more operations selected from the following operations (1) to (3).
(1) whisper (2) cry (3) move one of the four legs The voice determination means determines that the utterance of the spoken word uttered by the user is one or more words selected from the following (1) to (4) as an agreement request expression:
(1) "Ne"
(2) "U"
(3) "O"
(4) "ka"
When the ending of the spoken language given by the user is one or two words selected from the following words (5) and (6), it is determined to be a definitive expression,
(5) "Da"
(6) "Ya"
If the spoken language spoken by the user is not a consent request expression or assertive expression, it is determined as a normal expression,
The response response is a different response response by changing the number of times the crawl operation is performed,
The number of movements performed when determined as the consent request expression is greater than the number of movements performed when determined as the normal expression,
9. The communication robot according to claim 8, wherein the number of movements performed when it is determined as the assertion expression is greater than the number of movements performed when it is determined as the consent request expression.

Images